NVIDIA GeForce GTX 2070 Quick Binning Talk: TU106-400A vs. TU106-400



[ad_1]

EVGA GeForce RTX 2070 Ultra Gaming XC
EVGA is one of the few companies to publish multiple GeForce RTX series cards based on NVIDIA's reference specifications, and at reference prices (an important qualifier). This means that you can actually buy a GeForce RTX 2070 for $ 499.99, instead of paying a premium for the NVIDIA Overclocked Founders Edition model, or any of the many overclocked SKUs from the map partners. NVIDIA extension. EVGA, for example, is selling an overclocked GeForce RTX 2070 for $ 569.99. There may be more difference than the predefined specifications. More on that in a moment.
NVIDIA has marketed three cards: GeForce RTX 2080 Ti, GeForce RTX 2080 and GeForce RTX 2070. These three cards are available from NVIDIA as Founders Edition models, unlike the previous generation (Pascal). , FE models are overclocked. NVIDIA has also revised the cooling solution by exchanging the blower-type design for a cooler similar to that used by its AIB partners.

NVIDIA also announced reference specifications at lower prices, with the presumption that its AIB partners would offer both reference models and overclocked models. Here's how prices are set:

  • GeForce RTX 2080 Ti Edition of the founders: $ 1,199
  • GeForce RTX 2080 Ti Reference: 999 $
  • GeForce RTX 2080 Founders Edition: $ 799
  • GeForce RTX 2080 Reference: 699 $
  • GeForce RTX 2070 Edition of the founders: $ 599
  • GeForce RTX 2070 Reference: 499 $
EVGA GeForce RTX 2070 Black Gaming
Now, here is where things get interesting. Steve Burke at Nexus Gamers has gotten hold of two different EVGA models of GeForce RTX 2070, and more particularly on these …
  • EVGA GeForce RTX 2070 Ultra XC Games: $ 569.99
  • EVGA GeForce RTX 2070 Black Games: $ 499.99

Burke removed both cards to take a look at the GPU, and lo and behold, they are slightly different. The GPU under the hood of the Black Gaming Card is a TU106-400-A1 and the GPU of the XC Ultra Gaming is a TU106-400A-A1. Both are Turing GPUs and they are essentially the same in terms of specifications and features. However, it seems that the revision "A" is a grouped part that can run faster and keep its clock longer.

It is important to understand that not all tokens are the same. This applies to all semiconductors, whether it is a CPU, a GPU or RAM. In essence, you can buy two processors of the same model and see very different overclocking results. That's where binning comes in. Companies like NVIDIA have the ability to test and sort chips based on their ability to handle higher voltages and clock speeds.

At first glance, Burke seems to have discovered that NVIDIA bundled its Turing chips, which in turn sold two different versions to its card partners (at least for the GeForce RTX 2070). The TU106-400A-A1 is probably more expensive and therefore leads to higher priced cards with factory overclocking. Does it matter? As Burke notes when running both EVGA cards in 3DMark, it's possible.

"The XC Ultra measures an average of about 1935 MHz for the entire test, while the Black 2070 experiences a clock decay of about 1815 MHz to 1785 MHz. -The-Box, and indicates this advantage in terms of performance resulting from the best GPUs, "writes Burke.

Running overclocked specifications over reference clocks is usually a few frames per second, depending on the game and settings. However, it is interesting to note that the difference between a stored card and an overclocked card lies not only in the specifications, but also in the graphics processor. It's worth keeping in mind when buying a GeForce RTX card.

[ad_2]
Source link